Estimating 3D pose via stochastic search and expectation maximization

Authors:
Ben Daubney;Xianghua Xie
Affiliations:
Department of Computer Science, Swansea University, United Kingdom;Department of Computer Science, Swansea University, United Kingdom
Venue:
AMDO'10 Proceedings of the 6th international conference on Articulated motion and deformable objects
Year:
2010

Citing 7
Cited 0

Pictorial Structures for Object Recognition

International Journal of Computer Vision
Histograms of Oriented Gradients for Human Detection

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Variational Maximum A Posteriori by Annealed Mean Field Analysis

IEEE Transactions on Pattern Analysis and Machine Intelligence
Pattern Recognition and Machine Learning (Information Science and Statistics)

Pattern Recognition and Machine Learning (Information Science and Statistics)
HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human Motion

International Journal of Computer Vision
Multiple frame motion inference using belief propagation

FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
PAMPAS: real-valued graphical models for computer vision

CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper an approach is described to estimate 3D pose using a part based stochastic method. A proposed representation of the human body is explored defined over joints that employs full conditional models learnt between connected joints. This representation is compared against a popular alternative defined over parts using approximated limb conditionals. It is shown that using full limb conditionals results in a model that is far more representative of the original training data. Furthermore, it is demonstrated that Expectation Maximization is suitable for estimating 3D pose and better convergence is achieved when using full limb conditionals. To demonstrate the efficacy of the proposed method it is applied to the domain of 3D pose estimation using a single monocular image. Quantitative results are provided using the HumanEva dataset which confirm that the proposed method outperforms that of the competing part based model. In this work just a single model is learnt to represent all actions contained in the dataset which is applied to all subjects viewed from differing angles.